Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 562 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.4363. Min Act: -0.1700
Data Index: 2498249 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.4051. Min Act: -0.1700
Data Index: 4191722 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.3426. Min Act: -0.1700
Data Index: 3389243 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.3113. Min Act: -0.1700
Data Index: 4886902 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.3426. Min Act: -0.1700
Data Index: 5770987 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.3113. Min Act: -0.1700
Data Index: 3285688 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.3113. Min Act: -0.1700
Data Index: 7403370 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2801. Min Act: -0.1700
Data Index: 1394764 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2801. Min Act: -0.1700
Data Index: 4312527 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2801. Min Act: -0.1700
Data Index: 7380556 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2801. Min Act: -0.1700
Data Index: 6839828 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2801. Min Act: -0.1700
Data Index: 349607 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2801. Min Act: -0.1700
Data Index: 4498543 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2488. Min Act: -0.1700
Data Index: 6254510 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2801. Min Act: -0.1700
Data Index: 7914686 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2488. Min Act: -0.1700
Data Index: 2711701 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2488. Min Act: -0.1700
Data Index: 8608325 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2488. Min Act: -0.1700
Data Index: 5276221 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2488. Min Act: -0.1700
Data Index: 3794675 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4363. Min Range: -5.4363
Max Act: 5.2488. Min Act: -0.1700
Data Index: 4905792 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19